introspection-graphql-edge

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=true, so the description has room to add value and does: it quantifies the full-SDL cost (777,501 characters, ~194,000 tokens), explains that two thirds is repeated docstrings, and notes includeDescriptions:false as a mitigating lever. That is strong cost disclosure, but it stops short of describing result shape details such as pagination or truncation behavior on large type responses, keeping it from the top band.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The default behavior is front-loaded in the first clause, then the escalation path, then the size warning, then alternatives — a clean funnel. It is dense and every sentence carries information, but the token-size measurement and repeated cost cautions could be trimmed slightly without losing signal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description carries the full burden and does so: it states what the default call returns and roughly how large, what each parameter returns, and where to go instead for cheaper answers. An agent has everything needed to call this correctly and avoid the 194k-token trap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema itself already documents each parameter thoroughly, so the baseline would be 3. The description lifts this by adding decision-level semantics the schema lacks — that 'type' is the argument to reach for once the index gives you a name, and that 'full' should be reserved for genuine need given its measured size.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Explores the Sitecore GraphQL edge schema') and immediately defines the no-argument default output: root operations plus the Item interface. The 'edge' qualifier implicitly separates it from the master-schema introspection sibling, so an agent can tell which introspection tool it is holding.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing is given for every mode: no args for the index, type: for one definition, search: for discovery, and full: true 'only when you genuinely need every definition.' It goes further with negative guidance — prefer typed item/presentation tools, or authoring-get-item-template / common-get-item-field for template fields — naming actual sibling tools to use instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.